2022 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM)最新文献_第3页

Research and Implementation of Withstand Voltage Test Device 耐压试验装置的研究与实现

2022 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM) Pub Date : 2022-10-01 DOI: 10.1109/AIAM57466.2022.00095

Zhao Lei

引用次数: 0

Comprehensive analysis of a lower limb rehabilitation robot and its lightweight and simplification 综合分析一种下肢康复机器人及其轻量化和简化

2022 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM) Pub Date : 2022-10-01 DOI: 10.1109/AIAM57466.2022.00149

X. Lin, Xiaoshuo Wang, Weitian Wu

引用次数: 1

Implementation of Parallel Acceleration for Real-time Extraction of Visual Features 视觉特征实时提取的并行加速实现

2022 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM) Pub Date : 2022-10-01 DOI: 10.1109/AIAM57466.2022.00036

Ji-yang Yu, Dan Huang, Lu-yuan Wang, Miaomiao Tian, Tianzhu Zhang

{"title":"Implementation of Parallel Acceleration for Real-time Extraction of Visual Features","authors":"Ji-yang Yu, Dan Huang, Lu-yuan Wang, Miaomiao Tian, Tianzhu Zhang","doi":"10.1109/AIAM57466.2022.00036","DOIUrl":"https://doi.org/10.1109/AIAM57466.2022.00036","url":null,"abstract":"Visual feature extraction is the key to target localization, reconstruction and estimation. SIFT feature extraction algorithm has good adaptability and high computational complexity. In this paper, a parallel accelerated implementation of real-time extraction of visual SIFT features is designed. A parallel pipelined computing architecture is designed for the general SIFT computing process, and the data access is accelerated by combining DDR3, Block RAM and register three-level cache. Fixed-point computing is used in the computing modules of large data streams such as Gaussian pyramid, differential pyramid and extreme value detection. Hybrid precision is used in gradient histogram, feature description and matching process. When it comes to the calculation of exponential and trigonometric functions, the series expansion and table lookup method are adopted to effectively reduce the logic and storage occupation. In this paper, the design architecture and data information flow of each SIFT calculation module are given, and the whole design is verified experimentally in XC7K325. The results show that the design for 1024X1024 pixel image can reach 100 frames of calculation speed, power consumption is not more than 12W. The SIFT descriptor error is less than 1%, which ensures the calculation error of the system while the resources are effectively utilized.","PeriodicalId":439903,"journal":{"name":"2022 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114923498","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Small Sample Phase Selection Method Based on GASF and Swin-Transformer 基于GASF和摆动变压器的小样本选相方法

2022 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM) Pub Date : 2022-10-01 DOI: 10.1109/AIAM57466.2022.00065

Liang Zhao, Qiongfang Yu

引用次数: 1

Modal analysis of tethered UAV system under tension 系留无人机系统受拉模态分析

2022 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM) Pub Date : 2022-10-01 DOI: 10.1109/AIAM57466.2022.00099

Xing Longtao, Feng Zhizhuang, Liu Chen

{"title":"Modal analysis of tethered UAV system under tension","authors":"Xing Longtao, Feng Zhizhuang, Liu Chen","doi":"10.1109/AIAM57466.2022.00099","DOIUrl":"https://doi.org/10.1109/AIAM57466.2022.00099","url":null,"abstract":"In order to analyze the modal of the tethered UAV system, the motion of the UAV is treated as the boundary condition of the tether, and coupling dynamic model of the tethered UAV system is obtained. Considering the aerodynamic force of the tethered UAV system, the approximate expressions of the equilibrium tension and the equilibrium curvature of the tether are derived. On the basis of rebalancing analysis, the nonlinear equations of the tethered UAV system are linearized, and the normal natural frequencies and modes of the tethered cables are obtained. The influence of cable length and UAV load mass on the normal natural frequency and mode shape of mooring line is studied. It is found that with the increase of cable length and load mass, the forward second-order frequency of mooring method decreases continuously, and the normal second order frequency decreases more than the first order frequency. When the UAV’s load mass is fixed, the first normal mode shape of the mooring line changes little with the increase of the length of the mooring line. When the length of the cable is fixed, with the increase of the UAV load mass, the natural frequencies of the mooring method change little. When the wind excitation frequency of the system is close to the frequency of the system, the resonance of the system can be avoided by changing the length of the cable and load mass of the UAV to maintain the normal operation of the system. These studies provide a theoretical basis for the normal operation of the tethered UAV system.","PeriodicalId":439903,"journal":{"name":"2022 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127030568","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The Yellow River Walker Beach Garbage Robot 黄河沃克海滩垃圾机器人

2022 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM) Pub Date : 2022-10-01 DOI: 10.1109/AIAM57466.2022.00155

Chuang Zhao, Yuxuan Liu

引用次数: 0

K-Means Cluster Analysis Based on Consumer Behavior 基于消费者行为的k均值聚类分析

2022 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM) Pub Date : 2022-10-01 DOI: 10.1109/AIAM57466.2022.00034

Kunpeng Cai, Maria Rosario D. Rodavia

引用次数: 0

A Fast-Measuring Method for the Dielectric Spectrum of Power Cables 电力电缆介电谱的快速测量方法

2022 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM) Pub Date : 2022-10-01 DOI: 10.1109/AIAM57466.2022.00159

Qingyu Zhi, Sansheng Shi, Wen Wang, Siwei Guo, Yan Zhao

引用次数: 0

Contrastive Graph Learning for Session-based Recommendation 基于会话推荐的对比图学习

2022 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM) Pub Date : 2022-10-01 DOI: 10.1109/AIAM57466.2022.00033

Yan Chen, Dongqin Liu, Yipeng Su, Yan Zhou, Jizhong Han, Ruixuan Li

{"title":"Contrastive Graph Learning for Session-based Recommendation","authors":"Yan Chen, Dongqin Liu, Yipeng Su, Yan Zhou, Jizhong Han, Ruixuan Li","doi":"10.1109/AIAM57466.2022.00033","DOIUrl":"https://doi.org/10.1109/AIAM57466.2022.00033","url":null,"abstract":"In view of the problem that random deletion of graph nodes and edges may delete important item nodes when constructing graph structure enhancement samples in existing research work, which is not conducive to item node learning, this paper proposes a session-based recommendation method based on graph structure information enhancement. According to the importance of the nodes in the graph, the enhanced samples on the graph structure are constructed to enrich the representation of the item nodes. Firstly, our method constructs an item transfer graph according to the sequence of items interacted by the user, and then calculate the importance of the nodes and edges in the item transfer graph according to the in-degree and out-degree information of the user nodes in the graph. For important nodes and edges, we delete them with small probability. For the enhanced graph structure, we design contrastive learning on the graph structure to learn the representations of nodes on the graph. Finally, in the traditional conversation recommendation task, the auxiliary task of contrastive learning is added, and the multi-task learning framework is applied to learn the user's preference in session-based recommendation. Experimental results show that this method can effectively improve the performance of session sequence recommendation.","PeriodicalId":439903,"journal":{"name":"2022 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126552713","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Calculation and Analysis of Theoretical Line Loss Rate Based on Deep Learning Mechanism 基于深度学习机制的理论线损率计算与分析

2022 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM) Pub Date : 2022-10-01 DOI: 10.1109/AIAM57466.2022.00128

Gao Chen

{"title":"Calculation and Analysis of Theoretical Line Loss Rate Based on Deep Learning Mechanism","authors":"Gao Chen","doi":"10.1109/AIAM57466.2022.00128","DOIUrl":"https://doi.org/10.1109/AIAM57466.2022.00128","url":null,"abstract":"In the power industry system, line loss and line loss rate (L L R) are very important comprehensive indicators. The value of line loss directly affects the economic benefits of power companies, and is related to the vital interests of companies. It is not only important for the country to assess the power sector Economic indicators, colleagues can also reflect whether the grid structure and operation mode of a power grid are reasonable, and reflect the level of grid planning, power generation technology, and operation management. Based on this, the purpose of this article is to calculate and analyze the theoretical L L R based on the deep learning mechanism. This article first summarizes the theoretical basis of deep learning, and then studies the existing theoretical L L R calculation methods. On its basis, it is researched and analyzed in combination with the deep learning mechanism. This paper systematically explains the analysis process of the theoretical L L R based on the electrical network, the calculation method of the theoretical L L R based on DBN-DNN (D B N), and the theoretical L L R analysis based on the deep confidence network. And use comparative analysis method, observation method and other research methods to study the theme of this article. Experimental studies have shown that when the grid structure is unchanged, the DBN-DNN combined deep learning model proposed in this paper has a faster calculation speed, and the calculation result has a smaller deviation compared with the real result. The maximum error is 0.0077 and the minimum is 0.0011. Therefore, the deep learning model based on the DBN- DNN combination can accurately and quickly calculate the theoretical line loss rate when the grid structure is unchanged.","PeriodicalId":439903,"journal":{"name":"2022 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM)","volume":"65 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114091815","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0